This proof-of-concept project came about from a chance discussion in a meeting around biological data and data standards, where we were talking about hard copy data capture forms and how time-consuming it was to transcribe them into a database.  We have been working for some time on an AI service offering around transcription and so, we proposed to trial our Clio system to see if it could help solve the transcription problem for the Flora and Fauna team.

Imagine a bird survey containing several small plots at a site near Alice Springs, and over the course of 4-5 days the field scientist records the birds they observe or hear and other details. Information about each bird – such as its gender and age – is collected, if possible, to help in modelling population trends and understanding ecological processes. Once the field work is done, the notes are copied into a standard survey form. 

Input bird survey form

The hard copy forms contain a bunch of site information (e.g. siteID, surveyor’s name, coordinates, plot size, land descriptions etc.) and a number of visits at different times, with where observations of species are recorded as a list of occurrences.  Due to the complexity and rapid data collection techniques in the field, these surveys continue to be done with pen and paper. The forms build up across a team of field staff over the course of a year, and this then creates a significant backlog of time-consuming manual transcription work.

That’s where our team comes in. Gail Wittich is a Data Scientist at Gaia Resources and Hayden Richards is one of our Software Engineers who jumped at the chance to work on this proof-of-concept project. The outcome we were chasing was to see if we could significantly reduce that manual data entry time. I spoke to Gail about how she and Hayden tackled the challenge.

Were you just able to feed the scanned field survey forms in, and get the data out?

Not quite, but that was the general idea. We were able to save a significant amount of human processing time by first modifying the design of the survey form, and then introducing the AI algorithms to process the scans. Specifically, this uses Handwritten Character Recognition to read the forms and output a machine-readable file. The raw outputs from Clio also required some post-processing to fix some common spelling and format errors; but from there it was ready to have minor edits and curation performed by a human, before being ready as tabular data to import into the database. 

What does the processing approach look like?

The nt-birds-survey-tool is a proof-of-concept Python script for performing Clio text recognition on scanned PDFs, post-processing raw results and outputting tabular data as CSV files. We utilise cloud storage, tools and services from Amazon Web Services (AWS) to help bring this service together.

High level Technical Overview

The wonderful thing is that Clio gives a clear indication as to how well it is able to read each component of text, in the form of a Confidence Level (percentage) which can then be viewed chromatically to draw your attention to the problem areas for corrections. It also recognises form field and tabular information, and can export that into sensible data as rows and columns in a spreadsheet.

Clio prototype interface

What are some of the technical challenges you’ve come across?

AI has come a very long way in the last 20 years, and it is a rapidly evolving space; but for our line of work we are not talking about robots and algorithms that can pass the Turing test. For us, it comes down to helping scientists and researchers achieve time efficiencies and savings that they can apply to doing more good environmental work. As you can imagine with bird surveys, a person’s handwriting is not at its best when the person is writing on a clipboard or notepad and moving swiftly around in variable weather conditions. Complimenting the Clio raw result with standard post-processing techniques improves results significantly. It’s still tough for a machine to correctly read a 2 when it is written like a Z, for instance, but when you know the data is referring to a count of birds, you can be sure it is a 2. Or an S is a 5, and an I is a 1, and so on.   

Initially, Clio recognition was as low as 73% (73% of information on a form was correctly transcribed). In many cases this was just one or two letter differences or a  few numbers interpreted as letters. With the form design and a range of post-processing corrections like the ones above, we were able to increase accuracy to between 93% and 99%. We know that a successful implementation also requires a bit of training and reinforcement for field staff in how to use the form, but we were really pleased with those results. 

Why not just collect the data with a mobile app?

While we are big supporters of mobile apps and field technology solutions in the right situations, Clio is designed to support scanned content – current or historical. Just because we have the ability to build apps, doesn’t mean that every challenge will be solved by having one. Clio is ideal for the situations when people get back to basics – and use pencil on paper.

Why do you think this work is important?

Biodiversity data helps to answer important research questions and inform decisions on a variety of subjects, including: urban and rural development impacts, climate change and how it affects habitat and species populations and migration patterns. I work mainly with the data, but I can definitely see how we need reliable and efficient methods to generate and aggregate consistent, standardised data of this type to support research into those areas.

Where to from here?

We have proven that with some minimal redesign of form inputs, we can use this solution to get highly accurate transcriptions from these handwritten survey forms. We know it is going to save time, but this isn’t just about birds. There are many different types of flora and fauna surveys out there, including vegetation, mammals, reptiles, invertebrates and more – and several survey techniques and guidelines that define best practice in this space. We are concentrating on the survey forms, and I think the intent is that we can realise those time savings on many of those different types by following a similar process. We do need to run more tests and measure manual entry times for comparison. However, even if this saves 30 minutes in data entry per survey (not really a stretch when you think about it), for every thousand of these forms the payoff is 500 hours in time savings.

It’s really exciting to be undertaking proof-of-concepts like this one that allow us to leverage AI to help clients turn their scanned content into rich, standardised and reusable biodiversity data. We’ll have another blog a bit later to tell you about another Clio proof of concept project we’ve undertaken in the archives world – so stay tuned! 

If you’ve got data in a hard copy format that you need transcribed, then reach out to us and let’s see how we can help you solve your problems.  In the meantime, if you’d like to know more, start a conversation on our social media platforms – Twitter, LinkedIn or Facebook or send me an email.

Chris

The post Harnessing the Power of Artificial Intelligence to Capture Biodiversity Data appeared first on Gaia Resources.

I was never one of those kids who knew what they wanted to be when they grew up. Rather, I asked a lot of questions. Why do birds lay eggs? Who invented money? Why does sand clump when it’s wet, but fall apart when it’s too wet? I was nosy, driven by an obsession with understanding why things are. Inevitably, when I finished school I opted to study science. Science, by the way, comes from the latin word ‘Scire’ – to know. 

I specialised in biology. I loved the way that nature always had such elegant answer to complex problems. Learning about food webs, homeostasis and the carbon cycle fostered a view that everything is interconnected in a delicate balance. Growing up in Western Australia, I knew that the south-west of the continent is a biodiversity hotspot. Here’s the rub, though – that’s not a good thing: To be a ‘biodiversity hotspot’, an area must a) contain over 1,500 species of endemic vascular plants and b) have lost >70% of primary native vegetation. In short, Western Australia has exquisite vegetation needing protection and I took that personally.   

On graduation, I worked as a field scientist collecting botanical samples and traipsing around the Pilbara monitoring creeks. The work was interesting but the long hours took their toll and after two years I decided that it wasn’t for me. Field work is tough. In 2019 I went back to university, this time to complete a degree in environmental biotechnology: I was still fascinated by nature. I wanted to do something mentally stimulating and future-focussed. I needed better tools for saving the world.

One thing I’d struggled with in the workforce was how fractured the research could be. There was nothing holistic and a study conducted over there often had no bearing on what was happening over here – even if the subject matter was closely related. The research existed but there was nobody joining the dots. Going back to university allowed me to tap back into the pursuit of knowledge and focus on what could be instead of lamenting what is. During my studies, I had the privilege of learning from the state’s 10th Premier Fellow, who imparted a simple mantra: Look at the data. What do you see?

What I like about Gaia

I found Gaia Resources through google. No, really. I searched ‘environmental technology + Perth’, clicked the first hit and wrote to Piers to ask for a job. It was the first time a prospective employer had actually requested a sample of my work. (Look at the data – what do you see?). I sent Piers three of my best assignments and we realised quickly that we knew the same people. Small world …or at least, a close-knit community. 

Gaia Resources was winning the sort of projects that I wanted to do. Complex, interesting, future-focussed tech projects steeped in environmental science. Clients were taxonomists, microbiologists, geneticists and geologists. My coworkers are parasitologists, geographers and technology wiz kids. Everyone is obsessed with nature (or gaming). I’ve found my niche. 

I’m obviously biassed, but I feel that the projects I get to work on are meaningful, which is important to me. They are based on environmental concepts and mapping biodiversity. Our projects are nationally impactful, which keeps it exciting (and the pressure on to get things right). We’re aggregating information and archiving it for future generations. We’re connecting research. We’re building tools and making maps. 

Best of all, I’ve somehow landed a job where I’m actively encouraged to look for patterns, ask questions, join the dots and write what I see. I’m learning every day – and it’s a buzz to be working at the frontier of Australian environmental technology. 

If my story sounds appealing to you, why not start a conversation with us via email, or reach out on one of our social media platforms –  Twitter, LinkedIn or Facebook. We’d love to hear from you!

Claire

The post Valuing Biodiversity appeared first on Gaia Resources.

While sometimes it can seem like overwhelming cybersecurity threats abound, one of the topics that the speakers all seemed to agree upon was that we can take significant steps towards being cyber secure by simply making sure that users are kept up to date with relevant training and appreciation for the importance of their role in maintaining security for the technical assets of their organisation. Similarly for individuals, being aware particularly about what data they are sharing about themselves, and how it is being used. For organisations, one of the key factors to remember is human-centered design. Keeping practices and tools built to complement how people use them; solving problems for users rather than creating boundaries and rules that lead to regular frustration and occasional unsafe workarounds. 

Who hasn’t heard the story of someone who, frustrated with regular and complex password updates, kept a sticky note with their passwords on their desk?

Technology provides us with opportunities to solve so many problems. It is important to remember that as we integrate it so seamlessly into every aspect of our lives that we remain informed about the choices we are making by doing so. As well as understanding where both our rights and personal responsibilities lie, I think that we can all contribute something to the security of our personal information, as well as organisational assets by remaining willing to actively involve ourselves in opportunities to learn more about cybersecurity. 

As our world becomes more and more technically complex, we are inevitably going to be surrounded by various technologies that could theoretically become a risk – Internet of Things (IoT) devices are becoming commonplace, often our smartphones are both collecting and sharing a startling amount of personal data about ourselves – this doesn’t necessarily mean that we need to be terrified of it all, these devices can solve major challenges for us. But it does need to be addressed, by individuals, organisations and society as a whole.

Rather than being so afraid of the technical unknowns in our world, or missing out on advances from which we could greatly benefit, my personal opinion is that we need to pull our head out of the sand and learn what we are doing and what we could be doing to take responsibility and ownership of our own information and cybersecurity. From an organisational perspective, ensuring that technical teams working on cybersecurity truly understand how users are interacting with the system; so that processes are as intuitive and simple as possible to be both maintained and adhered to.

I would also like to take this opportunity to thank our very own Shay Telfer, whose rapid response to the Log4Shell vulnerability meant that we were able to bring solutions, not problems to those of our clients who may be affected.

I feel that the biggest take away from this Future Led session for me was a renewed interest in discovering more and learning what opportunities the future (particularly that of technology) might take us and what that means for the security of my own personal information.  If you have a technical challenge that you are interested in solving with a team that takes your security seriously send us an email or feel free to reach out on Facebook, Twitter or LinkedIn.

Sophie

The post Future Led: Overcoming the cybersecurity challenge appeared first on Gaia Resources.

From the remote sensing related challenges, one of them particularly caught my attention:  Identifying risk with science + communities, focusing on landslides. The challenge consisted of developing a tool using data from NASA satellites and ground-based sources to determine the risk of landslides in rural communities, and share the results with local communities and governments. I spoke to some friends about this, we decided to participate and registered as a team: the Landslide Detection Squad.

Trees tilting due to the effect of rock/soil sliding. Image credit mdpi.com

Before the event there was an information night held by Space Hub Perth and Core Innovation Hub, where speakers from BINAR, ICRAR and previous winners of the hackathon from Perth answered questions and gave us an insight of the current spatial situation in WA and Australia. It was a good chance to get motivation for working on spatial topics.

On the day of the hackathon, the team gathered at UWA Venture, excited to start the challenge. We kicked off by pitching some ideas and brainstorming on a white board, until we came up with what would be our project. Our objective was to detect the early stages of a landslide, with the purpose of warning the population living in risk areas. We needed to identify a parameter to measure that would indicate some kind of movement on the ground, so we chose trees. On forested slopes, tilting of trees and change in canopy structure can indicate soil and rock movement is occurring, which is a precursor to landslide events. Due to the use of remote sensing data, our tool could be applied in forested areas prone to landslide occurrence at a low cost.

Remote sensing data provides a low cost option to detect changes in canopy structure. Photo Credit

Photo Credit

Taking advantage of new sensors (e.g. cubesats and UAVs) providing high-resolution images and deep learning technologies for tree detection, we proposed and prototyped a method that detects a canopy movement on slopes that is indicative of landslide risk. This information could be used to enhance landslide risk models and is embedded within a system that generates dynamic risk maps, publishes alerts when situations are critical, and supports government agencies to plan ahead for emergency situations.

Spending the weekend doing something for science might not sound attractive to everyone, but it has its rewards! Chris from Gaia Resources, who was very supportive of my participation, suggested making this hackathon part of my professional development plan with the company. Taking part in this event allowed me to network with people from different backgrounds who are interested in the space field. As a team, we learned about landslides and prevention systems, and got the chance to build a new model which could help prevent disasters. 

However, that is not it: our team came first in Perth and our project will be competing in the global round! Now it is a matter of waiting for the global results. Even if we do not win, taking part in a hackathon was a great experience and I encourage everyone to try it!

Have you ever participated in a hackathon? How did you find the experience? Please share in the comments, or start a conversation with us on one of our social media platforms –  Twitter, LinkedIn or Facebook.

Rocío

The post NASA’s Space App Challenge: identifying landslide risk using remote sensing data appeared first on Gaia Resources.

Our newest paper Listening to Save Wildlife: Lessons Learnt from Use of Acoustic Technology by a Species Recovery Team, demonstrates how technology design research can reveal new opportunities, barriers, and future needs for conservation technology. Having been presented at the Designing Interactive Systems Conference in June, we would like to share it with you, as well as bonus pictures, sweet serenades of bristlebirds, and more about my work with the team!

The endangered Eastern Bristlebird (Dasyornis brachypterus)

There is little doubt that plants, animals, and ecosystems are declining at an alarming rate, and conservationists are looking for technology to support their tireless work to reverse these trends. In the early days of using technologies for conservation, the tools used were often created for other purposes (e.g. military or biomedical). Recently, conservationists have taken to developing their own technical solutions, exchanging experiences, opportunities, and barriers, such as through the conservation technology network WildLabs.Net or through social media channels (also see #Tech4Wildlife and newer #Tech4Wild).

A WildLabs.Net website screenshot

With the wonderfully burgeoning development of innovative conservation technologies has come new challenges. There is now an abundance of conservation technologies on the market that people can purchase, such as acoustic sensors and camera traps. These devices allow for massive amounts of data to be collected at a low cost, with minimal disturbance to the animals. This is certainly great, but before running off to purchase these devices we need to have a solid plan for what the data should look like, and what happens to it once we have it. In advance of purchasing devices, questions such as following should be considered:

• Are people going to use any particular data and metadata standards to ensure that the data can be easily shared for broadscale use?
• What biological and technical expertise is required to analyse the data? Do the volumes of data collected require a particular technological infrastructure to manage?
• How is the data going to be used, analysed, and managed?
• How can technologies be used to support conservation beyond locating and quantifying sneaky species? Are the data useful for conservation activities beyond simply finding the target critters?
• If so, what data analysis adaptations are needed? It’s worth thinking of these types of questions well in advance.

Check out the paper to learn about the Eastern Bristlebird Recovery Team’s goals, conservation activities, invaluable knowledge, and interest in acoustics, but even beyond that the team taught me a huge amount about efforts to save bristlebirds. Visiting Currumbin Wildlife Sanctuary several times, I learned for myself just how tricky these feathered beauties are to see and photograph, even when captive! Can you spot them?

While visiting the aviaries I learned about nesting behaviours of bristlebirds, and worked with the team to deploy sensors where keepers thought best to capture a variety of bristlebird calls. The keeper herself shared so much invaluable information about the calls with me while we worked together, and even challenged me to identify which individuals birds were making calls! I don’t have her skills! I also had the pleasure of meeting Penny, a former New South Wales Office of Environment and Heritage dog who assisted in the surveys to find Eastern bristlebirds in their wild habitats. She is now retired, but it was absolutely amazing watching how hard and efficiently she worked, bounding through tall grass, rapidly picking up the bristlebird scent during a training!

Once we brought the recorders back to the lab, I explored the audio data with team members playing audio of bristlebirds calling, while looking at associated visualisations of sound (i.e. spectrograms), and then discussing calls.

Call type 1

Call type 2

Call type 3

The team takes on a wide variety of tasks to combat the decline of Eastern bristlebirds, regularly evolving new techniques, and eagerly trying new technologies to improve bristlebird conservation outcomes.

From studying this team through a technology design lens, we identified 5 key aspects that warrant detailed consideration by both designers and conservationists to create innovative, impactful conservation technologies into the future.

1. Discern Goals & Motives: Understanding what is driving members of the group both individually and collectively can help share the technological infrastructure so that a variety of interests can be investigated with new
   data.

2. Improve Skills and Knowledge: Interested parties may lack the biological and/or technical skills required to collect and/or analyse data. It’s important to consider how technology can be designed to improve skills.

3. Facilitate Information Exchange: Technology has an important role to play in allowing people to share knowledge and exchange findings in new ways.

4. Extend Beyond the Team: Conservationists are often overburdened, and so it’s worthwhile considering what is needed for broader groups, such as citizen scientists, to participate in use of new technologies in
   conservation.

5. Design for Engagement, Usability, and Conservation Impact: When needing to review large quantities of data, it’s essential to design technology that is fun, usable, and produces accurate analysis to inform conservation efforts.

Technology designers have skills necessary to investigate such complex, wicked problems, and including technology design research in the conservation technology pipeline will reveal novel ways that technology could support conservation more effectively.

You can read Jessie’s complete post on the Queensland University of Technology’s Ecosounds site. You can also give us your feedback by comment below, start a chat with us via Facebook, Twitter or LinkedIn, or email directly via alex.chapman@gaiaresources.com.au.

The post Bristlebird Adventures: Designing Technology to Support Saving Wildlife appeared first on Gaia Resources.

Wifi at 30,000ft?

Last week I headed to Canberra for the Fenner Conference on the Environment: Urban Sustainability and Conservation, primarily to meet up with some of the Clean Air and Urban Landscapes Hub team and to participate in the conference (which was not your usual conference, more on that in a second).  My technology musings started at about 15 minutes after takeoff from Perth… when the cabin crew announced there is new, “high-speed” Wi-fi on domestic flights.  My first reaction was that there goes my little happy place of solitude at 30,000ft, but I was also pretty impressed that it was available.

The Fenner conference, held at the Shine Dome in Canberra, was an event I’m really glad I attended.  There were some thought-provoking presentations around landscape and building design and the environment, replacing trees with artificial ones, mygalamorph spiders in Perth, and unintended consequences of human-nature interactions (like urban wetlands for water treatment being new breeding grounds for mosquitoes).  It was also great to see Landcare represented (through the Corowa District Landcare group).

Apart from the talks, there was a considerable part of the day set aside for discussions towards how a statement around urban sustainability and conservation could be embraced, and in the afternoon session there was an interesting discussion around keeping us talking after the conference.  Immediately, everyone started suggesting forums, list servers, Facebook groups and the like, and I decided to pipe up.

My take on this comes from our work in citizen science, where it is really important to have engagement that is meaningful and preferably personal.  Alex has done a great job of presenting about that citizen science aspect in a couple of recent blogs, too.  Those forums and the like that were suggested above don’t work well for me, because they don’t deliver the same meaningful discussion we were having in the room.  So I suggested “as the IT guy” that you think about localised informal chapters that meet for coffee (or beer) to carry on these discussions.  There is yet to be a technology in the world is not a substitute for quality human interaction (especially when helped along with a beverage)!

Shiny dome at the Shine Dome (I couldn’t resist

I also spend quite a bit of time talking to a range of our clients in Canberra, including CSIRO, where we’re on the final stretch of our “upskilling” Collections Management project with the team behind the National Research Collections of Australia (NRCA).  Our project here has been to work alongside the CSIRO team, providing expertise, support and advice on the implementation of CollectiveAccess into the NRCA collections (more on that to come in a future blog).  A lot of that project has involved using technology to communicate – Confluence for tracking discussions and knowledge, Jira for tracking tasks, and a bunch of teleconferencing and videoconferencing to ensure that communication is as good as we can do remotely.  So technology was helping us communicate remotely, but wasn’t a complete substitute (we couldn’t just rely on Confluence and Jira).

I also managed across my travels to maintain something of a presence back in our offices, by being available to get into our team videoconferences, responding to emails, and working on a range of project deliverables while I was on the road.  Thank goodness for technology – on the way home I even used the in-flight wifi a bit (and to be honest, it’s still got teething problems) to catch up and try to clear the deck for the weekend.

Road warriors are powered by caffeine as much as technology

So I got home and recovered during the weekend (my fitness sure needs some work, but thankfully our new digs at FLUX have a gym) before heading straight back out to present yesterday at the Perth NRM Using Digital Technology in Natural Resource Management workshop.  I headed up the workshop with an introduction to technologies, providing some of our insights from working in this space for the last 15 years at Gaia Resources.  My slide deck is going out to the attendees as a PDF (which you can get here), and is embedded below.

The key messages from this presentation really riffed off the last week:

• Technology is not a magic bullet (and certainly doesn’t replace human interaction),
• Technology changes over time,
• Technology is no substitute for engagement, and
• Think about data standards, maintenance and collaboration.

It was a very interesting week all up which had me on something of a roller coaster ride, but it also has left me even more convinced that appropriate technology can help deliver great outcomes to the environment.  Seeing how well we can work remotely and how different technologies can help our clients to deliver on their needs, was a real refresher – something that kept me going through the pretty long days you get when you’re on the road (and catching up afterwards).

Technology for it’s own sake is not a good thing; but when you pair up a particular problem with appropriate technology? Well, that’s what gets me up and grinning every morning here at Gaia Resources, and we’re always looking for ways to help our clients – so drop me a line, or start a conversation with our team via Facebook, Twitter or LinkedIn.

Piers

The post Behind the scenes: Travels with Technology appeared first on Gaia Resources.